© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39205
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨æīĢ
    -0.07
    åīįæīĢæľª
    -0.06
    沫
    -0.06
    imoni
    -0.06
    ä¸īåĽĽ
    -0.06
    ìĤ¬
    -0.06
    нкÑĥ
    -0.06
    rollo
    -0.06
    usst
    -0.06
    åħ°åį¡
    -0.06
    POSITIVE LOGITS
    æ´»åĬ¨æŶ
    0.07
    Ñĭл
    0.07
    Flight
    0.07
    妮
    0.07
    hd
    0.07
    plr
    0.06
     Flight
    0.06
     Bru
    0.06
    aker
    0.06
    iele
    0.06
    Activations Density 0.286%

    No Known Activations